Hot spot detection based on feature space representation of visual search

This paper presents a new framework for capturing intrinsic visual search behavior of different observers in image understanding by analysing saccadic eye movements in feature space. The method is based on the information theory for identifying salient image features based on which visual search is performed. We demonstrate how to obtain feature space fixation density functions that are normalized to the image content along the scan paths. This allows a reliable identification of salient image features that can be mapped back to spatial space for highlighting regions of interest and attention selection. A two-color conjunction search experiment has been implemented to illustrate the theoretical framework of the proposed method including feature selection, hot spot detection, and back-projection. The practical value of the method is demonstrated with computed tomography image of centrilobular emphysema, and we discuss how the proposed framework can be used as a basis for decision support in medical image understanding.

[1]  H L Kundel,et al.  Searching for lung nodules. A comparison of human performance with random and systematic scanning models. , 1987, Investigative radiology.

[2]  H L Kundel,et al.  Searching for lung nodules. The guidance of visual scanning. , 1991, Investigative radiology.

[3]  A. L. I︠A︡rbus.  Eye Movements and Vision , 1967 .

[4]  Braithwaite Jj.  Visual search in space and time : where attention and inattention collide?. , 2002 .

[5]  Guang-Zhong Yang,et al.  The use of visual search for knowledge gathering in image decision support , 2002, IEEE Transactions on Medical Imaging.

[6]  Lawrence W. Stark,et al.  Visual perception and sequences of eye movement fixations: a stochastic modeling approach , 1992, IEEE Trans. Syst. Man Cybern..

[7]  P. Cavanagh,et al.  The Spatial Resolution of Visual Attention , 2001, Cognitive Psychology.

[8]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[9]  U. Neisser.  VISUAL SEARCH. , 1964, Scientific American.

[10]  Eyal M. Reingold,et al.  The Area Activation Model of Saccadic Selectivity in Visual Search , 2000 .

[11]  L. Stark,et al.  Scanpaths in Eye Movements during Pattern Perception , 1971, Science.

[12]  E. Krupinski,et al.  Searching for lung nodules. Visual dwell indicates locations of false-positive and false-negative decisions. , 1989, Investigative radiology.

[13]  R. Hess,et al.  Human peripheral spatial resolution for achromatic and chromatic stimuli: limits imposed by optical and retinal factors. , 1991, The Journal of physiology.

[14]  K. Preston White,et al.  Modeling human eye behavior during mammographic scanning: preliminary results , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[15]  D. M. Green,et al.  Signal detection theory and psychophysics , 1966 .

[16]  E. Conant,et al.  How experience and training influence mammography expertise. , 1999, Academic radiology.

[17]  S. Liversedge,et al.  Saccadic eye movements and cognition , 2000, Trends in Cognitive Sciences.

[18]  Francois Chabat.  Computed tomography image analysis for the detection of obstructive lung diseases , 2000 .

[19]  H L Kundel,et al.  Nature of expertise in searching mammograms for breast masses , 1996, Medical Imaging.